Computerized systems and methods facilitate preventing dangerous blood glucose levels using a predictive model to predict whether a particular patient is trending to have dangerous blood glucose levels. The predictive model may be built using logistic or linear regression models incorporating glucose data associated with a plurality of patients received from a plurality of sources. The glucose data may include context data and demographic data associated with the glucose data and the plurality of patients. The predictive model may be employed to predict a likelihood of a particular patient to have dangerous blood glucose levels. Based on the likelihood, the prediction and one or more interventions are communicated to a care team or the patient. The one or more interventions may be incorporated into a clinical device workflow associated with a clinician on the care team or the patient.
Legal claims defining the scope of protection, as filed with the USPTO.
1. One or more computer storage media storing computer-useable instructions, the instructions when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising: receiving, by an integrated home device associated with a patient, one or more interventions based on a determined real-time prediction, wherein the determined real-time prediction is based on analysis of a first set of glucose data corresponding to the patient by a predictive model trained by a second set of glucose data from a plurality of sources including electronic medical records associated with a plurality of patients, the determined real-time prediction indicating whether the patient is likely to have blood glucose levels corresponding to a predetermined threshold; and automatically adjusting a frequency or dosage of medication dispensed by the integrated home device associated with the patient based on the received one or more interventions, wherein training the predictive model includes logistic regression analysis of a plurality of data elements associated with the plurality of patients that are relevant to forecasting blood glucose levels, the plurality of data elements comprising at least one of medication data, clinical event data, surgical data, or demographic data, and wherein the first set of glucose data and the second set of glucose data includes blood glucose values and values for each of the plurality of data elements identified by the logistic regression analysis as relevant to forecasting blood glucose levels.
2. The one or more computer storage media of claim 1 , wherein the predictive model comprises one or more logistic or linear regression models.
3. The one or more computer storage media of claim 1 , wherein the predetermined threshold is ≥240 mg/dL or ≤70 mg/dL.
4. The one or more computer storage media of claim 1 , wherein the first set of glucose data comprises at least one of: a most recent glucose lab value; a month, a time, and a year the most recent glucose lab value was drawn; whether the most recent glucose lab value was drawn on a weekend; and an age, marital status, and race of the patient.
5. The one or more computer storage media of claim 2 , wherein the predetermined threshold is ≥240 mg/dL, and wherein the first set of glucose data comprises at least one of: a most recent glucose lab value; a month, a time, and a year the most recent glucose lab value was drawn; whether the most recent glucose lab value was drawn on a weekend; an age and race of the patient; geographic region where the most recent glucose lab value was drawn; and whether the most recent lab value was drawn at a teaching facility.
6. The one or more computer storage media of claim 2 , wherein the predetermined threshold is ≤70 mg/dL, and wherein the first set of glucose data comprises at least one of: a most recent glucose lab value; a month, a time, and a year the most recent glucose lab value was drawn; whether the most recent glucose lab value was drawn on a weekend; an age and race of the patient; geographic region where the most recent lab value was drawn; and whether the most recent lab value was drawn at a teaching facility.
7. The one or more computer storage media of claim 1 , wherein the one or more interventions include specific recommended actions.
8. The one or more computer storage media of claim 1 , the operations further comprising receiving additional data from a care team and the patient.
9. The one or more computer storage media of claim 8 , wherein the additional data includes data received from the patient in an electronic questionnaire communicated to the patient.
10. A computer-implemented method comprising: receiving, by an integrated home device associated with a patient, one or more interventions based on a determined real-time prediction, wherein the determined real-time prediction is based on analysis of a first set of glucose data corresponding to the patient by one or more predictive models trained by a second set of glucose data from a plurality of sources including electronic medical records associated with a plurality of patients, the determined real-time prediction indicating whether the patient is likely to have blood glucose levels corresponding to a predetermined threshold; automatically adjusting a frequency or dosage of medication dispensed by the integrated home device associated with the patient based on the received one or more interventions, wherein training the predictive model includes logistic regression analysis of a plurality of data elements associated with the plurality of patients that are relevant to forecasting blood glucose levels, the plurality of data elements comprising at least one of medication data, clinical event data, surgical data, or demographic data, and wherein the first set of glucose data and the second set of glucose data includes blood glucose values and values for each of the plurality of data elements identified by the logistic regression analysis as relevant to forecasting blood glucose levels.
11. The computer-implemented method of claim 10 , wherein the one or more predictive models comprises one or more logistic or linear regression models.
12. The computer-implemented method of claim 11 , wherein the predetermined threshold is ≥240 mg/dL, and wherein the first set of glucose data comprises at least one of: a most recent glucose lab value; a month, a time, and a year the most recent glucose lab value was drawn; whether the most recent glucose lab value was drawn on a weekend; an age and race of the patient; geographic region where the most recent lab value was drawn; and whether the most recent lab value was drawn at a teaching facility.
13. The computer-implemented method of claim 11 , wherein the predetermined threshold is ≤70 mg/dL, and wherein the first set of glucose data comprises at least one of: a most recent glucose lab value; a month, a time, and a year the most recent glucose lab value was drawn; whether the most recent glucose lab value was drawn on a weekend; an age and race of the patient; geographic region where the most recent lab value was drawn; and whether the most recent lab value was drawn at a teaching facility.
14. The computer-implemented method of claim 10 , wherein the predetermined threshold is ≥240 mg/dL or ≤70 mg/dL.
15. The computer-implemented method of claim 10 , wherein the first set of glucose data includes at least one of a most recent glucose lab value; a month, a time, and a year the most recent glucose lab value was drawn; whether the most recent glucose lab value was drawn on a weekend; and an age, marital status, and race of the patient.
16. The computer-implemented method of claim 10 , wherein the additional data includes data received from the patient in an electronic questionnaire communicated to the patient.
17. A system comprising: an integrated home device associated with a patient including one or more processors and one or more computer storage media storing instructions, the instructions when executed by the one or more processors, cause the one or more processors to: receive a one or more interventions based on a determined real-time prediction, wherein the determined real-time prediction is based on analysis of a first set of glucose data corresponding to the patient by a predictive model trained by a second set of glucose data from a plurality of sources including electronic medical records associated with a plurality of patients, the determined real-time prediction indicating whether the patient is likely to have blood glucose levels corresponding to a predetermined threshold; and automatically adjust a frequency or dosage of medication dispensed by the integrated home device associated with the patient based on the received one or more interventions, wherein training the predictive model includes logistic regression analysis of a plurality of data elements associated with the plurality of patients that are relevant to forecasting blood glucose levels, the plurality of data elements comprising at least one of medication data, clinical event data, surgical data, or demographic data, and wherein the first set of glucose data and the second set of glucose data includes blood glucose values and values for each of the plurality of data elements identified by the logistic regression analysis as relevant to forecasting blood glucose levels.
18. The system of claim 17 , further comprising a glucose database storing glucose data of the plurality of patients.
19. The system of claim 17 , wherein the predictive model comprises one or more logistic or linear regression models.
20. The system of claim 17 , wherein the predetermined threshold is ≥240 mg/dL or ≤70 mg/dL.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
September 13, 2018
January 12, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.